Anticipatory force planning during grasping is based on visual cues about the object’s physical properties and sensorimotor memories of previous actions with grasped objects. Vision can be used to estimate object mass based on the object size to identify and recall sensorimotor memories of previously manipulated objects. It is not known whether subjects can use density cues to identify the object’s center of mass (CM) and create compensatory moments in an anticipatory fashion during initial object lifts to prevent tilt. We asked subjects (n=8) to estimate CM location of visually symmetric objects of uniform densities (plastic or brass, symmetric CM) and non-uniform densities (mixture of plastic and brass, asymmetric CM). We then asked whether subjects can use density cues to scale fingertip forces when lifting the visually symmetric objects of uniform and non-uniform densities. Subjects were able to accurately estimate an object’s center of mass based on visual density cues. When the mass distribution was uniform, subjects could scale their fingertip forces in an anticipatory fashion based on the estimation. However, despite their ability to explicitly estimate CM location when object density was non-uniform, subjects were unable to scale their fingertip forces to create a compensatory moment and prevent tilt on initial lifts. Hefting object parts in the hand before the experiment did not affect this ability. This suggests a dichotomy between the ability to accurately identify the object’s CM location for objects with non-uniform density cues and the ability to utilize this information to correctly scale their fingertip forces. These results are discussed in the context of possible neural mechanisms underlying sensorimotor integration linking visual cues and anticipatory control of grasping.
LINK
Industrial robot manipulators are widely used for repetitive applications that require high precision, like pick-and-place. In many cases, the movements of industrial robot manipulators are hard-coded or manually defined, and need to be adjusted if the objects being manipulated change position. To increase flexibility, an industrial robot should be able to adjust its configuration in order to grasp objects in variable/unknown positions. This can be achieved by off-the-shelf vision-based solutions, but most require prior knowledge about each object tobe manipulated. To address this issue, this work presents a ROS-based deep reinforcement learning solution to robotic grasping for a Collaborative Robot (Cobot) using a depth camera. The solution uses deep Q-learning to process the color and depth images and generate a greedy policy used to define the robot action. The Q-values are estimated using Convolutional Neural Network (CNN) based on pre-trained models for feature extraction. Experiments were carried out in a simulated environment to compare the performance of four different pre-trained CNNmodels (RexNext, MobileNet, MNASNet and DenseNet). Results showthat the best performance in our application was reached by MobileNet,with an average of 84 % accuracy after training in simulated environment.
DOCUMENT
Parents who grew up without digital monitoring have a plethora of parental monitoring opportunities at their disposal. While they can engage in surveillance practices to safeguard their children, they also have to balance freedom against control. This research is based on in-depth interviews with eleven early adolescents and eleven parents to investigate everyday negotiations of parental monitoring. Parental monitoring is presented as a form of lateral surveillance because it entails parents engaging in surveillance practices to monitor their children. The results indicate that some parents are motivated to use digital monitoring tools to safeguard and guide their children, while others refrain from surveillance practices to prioritise freedom and trust. The most common forms of surveillance are location tracking and the monitoring of digital behaviour and screen time. Moreover, we provide unique insights into the use of student tracking systems as an impactful form of control. Early adolescents negotiate these parental monitoring practices, with responses ranging from acceptance to active forms of resistance. Some children also monitor their parents, showcasing a reciprocal form of lateral surveillance. In all families, monitoring practices are negotiated in open conversations that also foster digital resilience. This study shows that the concepts of parental monitoring and lateral surveillance fall short in grasping the reciprocal character of monitoring and the power dynamics in parent-child relations. We therefore propose that monitoring practices in families can best be understood as family surveillance, providing a novel concept to understand how surveillance is embedded in contemporary media practices among interconnected family members.
MULTIFILE
Studying images in social media poses specific methodological challenges, which in turn have directed scholarly attention toward the computational interpretation of visual data. When analyzing large numbers of images, both traditional content analysis as well as cultural analytics have proven valuable. However, these techniques do not take into account the contextualization of images within a socio-technical environment. As the meaning of social media images is co-created by online publics, bound through networked practices, these visuals should be analyzed on the level of their networked contextualization. Although machine vision is increasingly adept at recognizing faces and features, its performance in grasping the meaning of social media images remains limited. Combining automated analyses of images with platform data opens up the possibility to study images in the context of their resonance within and across online discursive spaces. This article explores the capacities of hashtags and retweet counts to complement the automated assessment of social media images, doing justice to both the visual elements of an image and the contextual elements encoded through the hashtag practices of networked publics.
DOCUMENT
Studying images in social media poses specific methodological challenges, which in turn have directed scholarly attention towards the computational interpretation of visual data. When analyzing large numbers of images, both traditional content analysis as well as cultural analytics have proven valuable. However, these techniques do not take into account the circulation and contextualization of images within a socio-technical environment. As the meaning of social media images is co-created by networked publics, bound through networked practices, these visuals should be analyzed on the level of their networked contextualization. Although machine vision is increasingly adept at recognizing faces and features, its performance in grasping the meaning of social media images is limited. However, combining automated analyses of images - broken down by their compositional elements - with repurposing platform data opens up the possibility to study images in the context of their resonance within and across online discursive spaces. This paper explores the capacities of platform data - hashtag modularity and retweet counts - to complement the automated assessment of social media images; doing justice to both the visual elements of an image and the contextual elements encoded by networked publics that co-create meaning.
MULTIFILE
Like a marker pen on a map, the Covid-19 pandemic drastically highlighted the persisting existence of borders that used to play an ever decreasing role in people´s perception and behavior over the last decades. Yes, inner European borders are open in normal times. Yes, people, goods, services and ideas are crossing the border between Germany and the Netherlands freely. Yet we see that the border can turn into a barrier again quickly and effectively and it does so in many dimensions, some of them being not easily visible. Barriers hinder growth, development and exchange and in spite of our progress in creating a borderless Europe, borders still create barriers in many domains. Differing labor law, social security and tax systems, heterogeneous education models, small and big cultural differences, language barriers and more can impose severe limitations on people and businesses as they cross the border to travel, shop, work, hire, produce, buy, sell, study and research. Borders are of all times and will therefore always exist. But as they did so for a long time, huge opportunities can be found in overcoming the barriers they create. The border must not necessarily be a dividing line between two systems. It has the potential to become a center of growth and progress that build on joint efforts, cross-border cooperation, mutual learning and healthy competition. Developing this inherent potential of border regions asks for politics, businesses and research & education on both sides of the border to work together. The research group Cross-Border Business Development at Fontys University of Applied Science in Venlo conducts applied research on the impact of the national border on people and businesses in the Dutch-German border area. Students, employees, border commuters, entrepreneurs and employers all face opportunities as well as challenges due to the border. In collaboration with these stakeholders, the research chair aims to create knowledge and provide solutions towards a Dutch-German labor market, an innovative Dutch-German borderland and a futureproof Cross-Border economic ecosystem. This collection is not about the borderland in times of COVID-19. Giving meaning to the borderland is an ongoing process that started long before the pandemic and will continue far beyond. The links that have been established across the border and those that will in the future are multifaceted and so are the topics in this collection. Vincent Pijnenburg outlines a broader and introductory perspective on the dynamics in the Dutch-German borderland.. Carla Arts observes shopping behavior of cross-border consumers in the Euregion Rhine-Meuse-North. Jan Lucas explores the interdependencies of the Dutch and German economies. Jean Louis Steevensz presents a cross-border co-creation servitization project between a Dutch supplier and a German customer. Vincent Pijnenburg and Patrick Szillat analyze the exitence of clusters in the Dutch-German borderland. Christina Masch and Janina Ulrich provide research on students job search preferences with a focus on the cross-border labor market. Sonja Floto-Stammen and Natalia Naranjo-Guevara contribute a study of the market for insect-based food in Germany and the Netherlands. Niklas Meisel investigates the differences in the German and Dutch response to the Covid-19 crisis. Finally, Tolga Yildiz and Patrick Szillat show differences in product-orientation and customer-orientation between Dutch and German small and medium sized companies. This collection shows how rich and different the links across the border are and how manifold the perspectives and fields for a cross-border approach to regional development can be. This publication is as well an invitation. Grasping the opportunities that the border location entails requires cooperation across professional fields and scientific disciplines, between politics, business and researchers. It needs the contact with and the contribution of the people in the region. So do what we strive for with our cross-border research agenda: connect!
DOCUMENT
Force transmission across the wrist during a grasping maneuver of the hand was simulated for three children with juvenile idiopathic arthritis (JIA) and for one healthy age-matched child. Joint reaction forces were estimated using a series of springs between articulating bones. This method (i.e., rigid body spring modeling) has proven useful for examining loading profiles for normally aligned wrists. A novel method (i.e., sliding rigid body spring modeling) designed specifically for studying joint reaction forces of the malaligned JIA wrist is presented in this paper. Loading profiles across the wrist for the unimpaired child were similar using both spring modeling methods. However, the traditional fixed-end method failed to converge to a solution for one of the JIA subjects indicating the sliding model may be more suitable for investigating loading profiles of the malaligned wrist. The results of this study suggest that a larger proportion of force is transferred through the ulno-carpal joint of the JIA wrist than for healthy subjects, with a less than normal proportion of force transferred through the radio-carpal joint. In addition, the ulnar directed forces along the shear axis defined in this study were greater for all three JIA children compared to values for the healthy child. These observations are what were hypothesized for an individual with JIA of the wrist.
DOCUMENT
The number of applications in which industrial robots share their working environment with people is increasing. Robots appropriate for such applications are equipped with safety systems according to ISO/TS 15066:2016 and are often referred to as collaborative robots (cobots). Due to the nature of human-robot collaboration, the working environment of cobots is subjected to unforeseeable modifications caused by people. Vision systems are often used to increase the adaptability of cobots, but they usually require knowledge of the objects to be manipulated. The application of machine learning techniques can increase the flexibility by enabling the control system of a cobot to continuously learn and adapt to unexpected changes in the working environment. In this paper we address this issue by investigating the use of Reinforcement Learning (RL) to control a cobot to perform pick-and-place tasks. We present the implementation of a control system that can adapt to changes in position and enables a cobot to grasp objects which were not part of the training. Our proposed system uses deep Q-learning to process color and depth images and generates an (Formula presented.) -greedy policy to define robot actions. The Q-values are estimated using Convolution Neural Networks (CNNs) based on pre-trained models for feature extraction. To reduce training time, we implement a simulation environment to first train the RL agent, then we apply the resulting system on a real cobot. System performance is compared when using the pre-trained CNN models ResNext, DenseNet, MobileNet, and MNASNet. Simulation and experimental results validate the proposed approach and show that our system reaches a grasping success rate of 89.9% when manipulating a never-seen object operating with the pre-trained CNN model MobileNet.
DOCUMENT
Conceptual metaphors play a vital role in our ability to think in abstract terms like knowledge. Metaphors structure and give meaning to the concept of knowledge. They hide and highlight certain characteristics. The choice of metaphor when reasoning about knowledge is therefore of vital importance for knowledge management (KM). This paper explores the possibility of introducing new knowledge metaphors to the field of KM. Based on a ‘wish list’ of characteristics of knowledge they want to highlight, the authors choose to explore the Knowledge as a Journey metaphor as a new metaphor for knowledge. This results in new insights regarding knowledge sharing, acquisition, retention, and innovation.
DOCUMENT
Conceptual metaphors play a vital role in our ability to think in abstract terms like knowledge. Metaphors structure and give meaning to the concept of knowledge. They hide and highlight certain characteristics. The choice of metaphor when reasoning about knowledge is therefore of vital importance for knowledge management (KM). This paper explores the possibility of introducing new knowledge metaphors to the field of KM. Based on a ‘wish list’ of characteristics of knowledge they want to highlight, the authors choose to explore the Knowledge as a Journey metaphor as a new metaphor for knowledge. This results in new insights regarding knowledge sharing, acquisition, retention, and innovation.
DOCUMENT
